mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-24 09:26:08 +00:00
bc791d53f4
Adds OpenSearch as a source and destination. Since OpenSearch is a fork of Elasticsearch, these connectors rely heavily on inheriting the Elasticsearch connectors whenever possible. - Adds OpenSearch source connector to be able to ingest documents from OpenSearch. - Adds OpenSearch destination connector to be able to ingest documents from any supported source, embed them and write the embeddings / documents into OpenSearch. - Defines an example unstructured elements schema for users to be able to setup their unstructured OpenSearch indexes easily. --------- Co-authored-by: potter-potter <david.potter@gmail.com>
48 lines
1.6 KiB
ReStructuredText
48 lines
1.6 KiB
ReStructuredText
OpenSearch
|
|
==============
|
|
Connect OpenSearch to your preprocessing pipeline, and batch process all your documents using ``unstructured-ingest`` to store structured outputs locally on your filesystem.
|
|
|
|
First you'll need to install the OpenSearch dependencies as shown here.
|
|
|
|
.. code:: shell
|
|
|
|
pip install "unstructured[opensearch]"
|
|
|
|
Run Locally
|
|
-----------
|
|
|
|
.. tabs::
|
|
|
|
.. tab:: Shell
|
|
|
|
.. literalinclude:: ./code/bash/opensearch.sh
|
|
:language: bash
|
|
|
|
.. tab:: Python
|
|
|
|
.. literalinclude:: ./code/python/opensearch.py
|
|
:language: python
|
|
|
|
Run via the API
|
|
---------------
|
|
|
|
You can also use upstream connectors with the ``unstructured`` API. For this you'll need to use the ``--partition-by-api`` flag and pass in your API key with ``--api-key``.
|
|
|
|
.. tabs::
|
|
|
|
.. tab:: Shell
|
|
|
|
.. literalinclude:: ./code/bash/opensearch_api.sh
|
|
:language: bash
|
|
|
|
.. tab:: Python
|
|
|
|
.. literalinclude:: ./code/python/opensearch_api.py
|
|
:language: python
|
|
|
|
Additionally, you will need to pass the ``--partition-endpoint`` if you're running the API locally. You can find more information about the ``unstructured`` API `here <https://github.com/Unstructured-IO/unstructured-api>`_.
|
|
|
|
For a full list of the options the CLI accepts check ``unstructured-ingest opensearch --help``.
|
|
|
|
NOTE: Keep in mind that you will need to have all the appropriate extras and dependencies for the file types of the documents contained in your data storage platform if you're running this locally. You can find more information about this in the `installation guide <https://unstructured-io.github.io/unstructured/installing.html>`_.
|